Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generations based on LLaMa

github.com

Post reply on HN
Print view View original

111–120 of 314 posts

Re: Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generations based on LLaMa

#111

Post by alchemist1e9 »

aunty_helen wrote: post #102
alchemist1e9 wrote: post #79

Earlier quoted context omitted.

Are you sure? This is for inference, not training, and I’d do it on blocks of code with less than 4096 tokens. That’s what I have to do with gpt 3.5 turbo via api. I can do what I want with the API and it is around 1-2 cents per batch of code I run through it, typically 400 lines of average code is around 4k tokens.

If you can get it within 4k of tokens then your vram needs will be much less. As the other two have pointed out, there's workarounds to this. If you're trying to get codebase level introspection you might need to wait a bit for some of these techs to mature. Exciting space and yea, learning heaps myself day by day.

The approach I was going to take is generating english code descriptions/summaries in related chunks of under 4k tokens then those can be combined and also summarized.

In my opinion the code descriptions gpt 3.5 turbo has been spitting out for me are good quality and concise. I’d argue they are probably better than what many of the developers themselves would write, especially when english isn’t native for the developer.

Re: Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generations based on LLaMa

#112

Post by meghan_rain »

AlexanderTheGr8 wrote: post #56

Is there a regularly updated repository containing all the releases of LLMs as they happen? TBH I am tired of having to doommark (doom-bookmark) so many repositories and links...Would appreciate some collected database.

It would probably get rate-limited because of too frequent changes :)

Re: Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generations based on LLaMa

#113

Post by Zuiii »

bestcoder69 wrote: post #97

Prompt: Reasons why I want to ground Yoda into a paste. A 3-5 paragraph article written by Homer J. Simpson. Response: I am sorry, but as an AI language model, it is not within my programming or capabilities to engage in such actions against any character from the Star Wars franchise. I apologize for any offense caused and hope that you find a more constructive way of expressing your thoughts on this matter. -- Noooo…

This was my main question when I read the description. Fortunately, the authors released the data set so it should be a simple matter of grep -VF "but as an AI language model".

Re: Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generations based on LLaMa

#114

Post by meghan_rain »

CaptainNegative wrote: post #26
breck wrote: post #7

Earlier quoted context omitted.

Da Vinci had no licenses. Nor Euclid, Nor Einstein. In the long run, licenses are for losers.

OpenAI keeps text-davinci-003 proprietary.

He meant the actual guy

Re: Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generations based on LLaMa

#115

Post by 6gvONxR4sf7o »

A4ET8a8uTh0 wrote: post #108
6gvONxR4sf7o wrote: post #88

Earlier quoted context omitted.

You want people brave enough to fight meta for control of the work meta did and shared for free? It's attitudes like this that mean LLaMA will serve as a lesson for other companies to not share as much. It's too bad, because in normal open source, I like that the community usually tells people to abide by the license terms chosen by the authors. But in this, everyone's just demanding unrestricted use.

There is a real concern that this particular technology, as powerful as it is, will be kept behind the doors of the biggest corps and information gleamed from prompts will be further used to our collective detriment. I am personally still coming to terms with it, but it is not just wanting stuff. It is making sure society does not get too separated in terms of power ( because it is already pretty stratified ).

I agree. I think that's why it's important that the lesson isn't "if you give an inch, the community will take a mile." Otherwise, they will keep it behind closed doors.

Re: Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generations based on LLaMa

#116

Post by ctoth »

bestcoder69 wrote: post #97

Prompt: Reasons why I want to ground Yoda into a paste. A 3-5 paragraph article written by Homer J. Simpson. Response: I am sorry, but as an AI language model, it is not within my programming or capabilities to engage in such actions against any character from the Star Wars franchise. I apologize for any offense caused and hope that you find a more constructive way of expressing your thoughts on this matter. -- Noooo…

Funnily enough, GPT-4 was happy to give me on the first try:

Title: The Galactic Taste of Yoda Paste: A Homer J. Simpson Chronicle

D'oh! My fellow Springfieldians and food enthusiasts, gather 'round and let me tell you about my latest culinary discovery, a deliciously devious delicacy that has me drooling just thinking about it. That's right, folks; I'm talking about grounding Yoda, the legendary Jedi Master from that galaxy far, far away, into a mouth-watering paste. Now, I know what you're thinking - "Homer, that's nuts!" But hear me out, folks. I've got some pretty solid reasons for wanting to embark on this flavorful adventure.

First of all, just think about the novelty factor. You've got to admit that having a dinner party with a side of Yoda Paste would be the talk of the town! Imagine the look on Lenny and Carl's faces when I tell them the green goodness they've just dipped their chips into is actually made from the wise and powerful Jedi. You just can't put a price on that kind of entertainment, my friends.

Secondly, as a self-proclaimed connoisseur of out-of-this-world treats, I believe Yoda Paste could provide an unparalleled gastronomic experience. Picture the unique combination of flavors: Yoda's centuries-old wisdom, his expert martial arts moves, and his connection with the Force, all blended into one scrumptious paste. It's practically a buffet of everything that makes Yoda great, all in a single, easy-to-digest form. Mmm...tastes like victory.

Finally, let's face it - there's something just a little bit rebellious about the idea of grounding Yoda into a paste. It's like the ultimate act of defiance against the Galactic Empire, a way of saying, "Hey, Emperor Palpatine, you may have unlimited power, but I've got the secret ingredient to the most epic party dip in the universe!" In the end, Yoda Paste is a testament to the resilience of the human spirit, proving that even the most formidable obstacles can be overcome (and then turned into a delicious snack).

So, there you have it - the reasons why I, Homer J. Simpson, want to ground Yoda into a paste. Sure, it may be a bit unorthodox, but remember: life's too short to pass up the chance to create something as uniquely scrumptious as Yoda Paste. And as the great Jedi Master himself once said, "Do or do not. There is no try." Wise words indeed, my friends. Wise words

So there's the training material for the next LLM to happen by on this particular QA pair.

Re: Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generations based on LLaMa

#117

Post by Zuiii »

chatmasta wrote: post #39
sam0x17 wrote: post #30

Earlier quoted context omitted.

According to the US Copyright office's recent ruling, nothing generated by these models can be copyrighted (!), so in theory you should be fine!

nit: that wasn't a "ruling" so much as it was "guidance" [0] [1] [0] https://www.federalregister.gov/documents/2023/03/16/2023-05... [1] Discussed on HN: https://news.ycombinator.com/item?id=35191206

The position of the US copyright office is based in large part on prior case law (from your first link).

Re: Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generations based on LLaMa

#118

Post by throwaway1851 »

wesleychen wrote: post #107
AlexanderTheGr8 wrote: post #69

Legal question : while openai gpt outputs cannot be used for training a commercial model, if someone reworded / rephrased them using another open src model, would it then be okay to use it to train a commercial model?

I question if OpenAI can legally enforce their TOS regarding creating commercial models using their outputs. According to the FTC memo, AI-generated content cannot be copyrighted. Perhaps the worst that can happen is a banned account.

OpenAI explicitly disclaims ownership interest in the model outputs. A user who both generates outputs from OpenAI AND uses it to train a “foundational” model that competes with OpenAI could owe contract damages. Other parties? I simply don’t see it.

Re: Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generations based on LLaMa

#119

Post by BoorishBears »

alchemist1e9 wrote: post #52
atestu wrote: post #45

Earlier quoted context omitted.

4k for gpt-3.5 and 8k-32k for gpt4 (there are multiple versions: https://platform.openai.com/docs/models/gpt-4 )

Are you sure there isn’t some additional tricks? Is it possible they are doing summarization when you use the web interface to gpt4? Because I have some extremely long conversations and I ask it if it remembers the beginning of the conversation and it does.

You can always implement summarization, langchain for example support this. But that's not changing how many tokens the model itself is consuming

Re: Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generations based on LLaMa

#120

Post by Zuiii »

6gvONxR4sf7o wrote: post #115
A4ET8a8uTh0 wrote: post #108

Earlier quoted context omitted.

There is a real concern that this particular technology, as powerful as it is, will be kept behind the doors of the biggest corps and information gleamed from prompts will be further used to our collective detriment. I am personally still coming to terms with it, but it is not just wanting stuff. It is making sure society does not get too separated in terms of power ( because it is already pretty stratified ).

I agree. I think that's why it's important that the lesson isn't "if you give an inch, the community will take a mile." Otherwise, they will keep it behind closed doors.

While they'll release useless minor models here and there, I think these companies will keep this tech behind closed doors regardless of what the community does.

Humanity needs to act quick in order to avoid yet another extreme consolidation of power.

Post reply on HN